DRL-based Dolph-Tschebyscheff Beamforming in Downlink Transmission for Mobile Users
Nancy Nayak, Kin K. Leung, Lajos Hanzo
TL;DR
The paper addresses blind beamforming for downlink mmWave MIMO in multi-BS networks without CSI. It introduces a DRL framework employing a learnable Dolph-Tschebyscheff planar antenna (LDTPA) whose major-to-minor lobe ratio $r_j$ is learned online to balance beamwidth and side-lobes, thereby reducing inter-user interference as the UE set varies. The method casts beam pattern control as a Markov decision process and uses Deep Deterministic Policy Gradient (DDPG) with a shared feature extractor and per-UE sub-networks to predict BS assignment, beam angles, and $r_j$, with a closed-form relation $r_j = R_0\times(\tilde{a}^{(j)}_{r}+p)/q$ guiding the voltage ratio. Simulation results show that LDTPA dramatically narrows the performance gap to an Oracle and outperforms UPA-based DRL-BA, especially for larger antenna configurations, highlighting improved spectral efficiency and angular selectivity for sensing and communications in dynamic dense networks.
Abstract
With the emergence of AI technologies in next-generation communication systems, machine learning plays a pivotal role due to its ability to address high-dimensional, non-stationary optimization problems within dynamic environments while maintaining computational efficiency. One such application is directional beamforming, achieved through learning-based blind beamforming techniques that utilize already existing radio frequency (RF) fingerprints of the user equipment obtained from the base stations and eliminate the need for additional hardware or channel and angle estimations. However, as the number of users and antenna dimensions increase, thereby expanding the problem's complexity, the learning process becomes increasingly challenging, and the performance of the learning-based method cannot match that of the optimal solution. In such a scenario, we propose a deep reinforcement learning-based blind beamforming technique using a learnable Dolph-Tschebyscheff antenna array that can change its beam pattern to accommodate mobile users. Our simulation results show that the proposed method can support data rates very close to the best possible values.